theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-20 23:58:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

bugfix & update doc

Browse Source
This commit is contained in:
Artiprocher
2025-12-04 10:35:14 +08:00
parent 4a15618080
commit 7747f38561
6 changed files with 768 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
diffsynth/models/z_image_dit.py
View File

@@ -537,7 +537,7 @@ class ZImageDiT(nn.Module):
x = torch.cat(x, dim=0)
x = self.all_x_embedder[f"{patch_size}-{f_patch_size}"](x)
x[torch.cat(x_inner_pad_mask)] = self.x_pad_token
x[torch.cat(x_inner_pad_mask)] = self.x_pad_token.to(dtype=x.dtype, device=x.device)
x = list(x.split(x_item_seqlens, dim=0))
x_freqs_cis = list(self.rope_embedder(torch.cat(x_pos_ids, dim=0)).split(x_item_seqlens, dim=0))
@@ -565,7 +565,7 @@ class ZImageDiT(nn.Module):
cap_feats = torch.cat(cap_feats, dim=0)
cap_feats = self.cap_embedder(cap_feats)
cap_feats[torch.cat(cap_inner_pad_mask)] = self.cap_pad_token
cap_feats[torch.cat(cap_inner_pad_mask)] = self.cap_pad_token.to(dtype=x.dtype, device=x.device)
cap_feats = list(cap_feats.split(cap_item_seqlens, dim=0))
cap_freqs_cis = list(self.rope_embedder(torch.cat(cap_pos_ids, dim=0)).split(cap_item_seqlens, dim=0))